Modifying deepstream-yolov4 code for yolov5

Accelerated Computing Intelligent Video Analytics DeepStream SDK
1

Please provide complete information as applicable to your setup.

• Hardware Platform (Jetson / GPU) AGX Xavier
• DeepStream Version 6.0
• JetPack Version (valid for Jetson only) 4.6
• TensorRT Version 8
• NVIDIA GPU Driver Version (valid for GPU only)
• Issue Type( questions, new requirements, bugs)
• How to reproduce the issue ? (This is for bugs. Including which sample app is using, the configuration files content, the command line used and other details for reproducing)
• Requirement details( This is for new requirement. Including the module name-for which plugin or for which sample application, the function description)

Continuing the discussion from About deepstream sdk with yolov5: I am looking to run a custom trained yolov5 model in Deepstream. I modified the nvdsparsebbox_Yolo.cpp file to change the number of classes, but when I ran the code, I saw an assert at Line 139 - “assert(boxes.inferDims.numDims == 3);”. While I am expecting that the code needs to be modified, I am not sure how the outputs are structured in Yolov5. Can any of you give me some insight to how the structure of Yolov5 is different from that of Yolov4?

Thank you!

3

Hi,

Please note that we have a newer Deepstream 6.0.1 release.
It’s recommended to upgrade your environment to the latest for a better experience.

Back to your question, below is an example for YOLOv5 from the community.
It should be able to give you some idea about the customized YOLO output parser:

Thanks.

5

This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.